eval_results/HuggingFaceH4/zephyr-7b-beta-ift/v1.1/ifeval/results_2024-03-13T16-29-54.450273.json

{
  "config_general": {
    "lighteval_sha": "?",
    "num_fewshot_seeds": 1,
    "override_batch_size": 4,
    "max_samples": null,
    "job_id": "",
    "start_time": 1129472.698786851,
    "end_time": 1130353.901131546,
    "total_evaluation_time_secondes": "881.2023446948733",
    "model_name": "HuggingFaceH4/zephyr-7b-beta-ift",
    "model_sha": "cbfb7849e2a2c7018cb2c948c5056197cbed1327",
    "model_dtype": "torch.bfloat16",
    "model_size": "13.99 GB",
    "config": null
  },
  "results": {
    "custom|ifeval|0": {
      "prompt_level_strict_acc": 0.08687615526802218,
      "prompt_level_strict_acc_stderr": 0.01212043643892942,
      "inst_level_strict_acc": 0.17026378896882494,
      "inst_level_strict_acc_stderr": 0.000410042642083444,
      "prompt_level_loose_acc": 0.09426987060998152,
      "prompt_level_loose_acc_stderr": 0.012574449557583902,
      "inst_level_loose_acc": 0.18345323741007194,
      "inst_level_loose_acc_stderr": 0.00041812354558558263
    }
  },
  "versions": {
    "custom|ifeval|0": 0
  },
  "config_tasks": {
    "custom|ifeval": {
      "name": "ifeval",
      "prompt_function": "ifeval_prompt",
      "hf_repo": "wis-k/instruction-following-eval",
      "hf_subset": "default",
      "metric": [
        "ifeval_metric"
      ],
      "hf_avail_splits": [
        "train"
      ],
      "evaluation_splits": [
        "train"
      ],
      "few_shots_split": "train",
      "few_shots_select": "random_sampling",
      "generation_size": 1280,
      "stop_sequence": [],
      "output_regex": null,
      "frozen": false,
      "suite": [
        "custom"
      ],
      "original_num_docs": 541,
      "effective_num_docs": 541,
      "trust_dataset": null
    }
  },
  "summary_tasks": {
    "custom|ifeval|0": {
      "hashes": {
        "hash_examples": "e99cbf567588d7c6",
        "hash_full_prompts": "7ea7bf2a8edba8f4",
        "hash_input_tokens": "1674fbca8428210a",
        "hash_cont_tokens": "9cb9a63fc8a83a6b"
      },
      "truncated": 0,
      "non_truncated": 541,
      "padded": 0,
      "non_padded": 541,
      "effective_few_shots": 0.0,
      "num_truncated_few_shots": 0
    }
  },
  "summary_general": {
    "hashes": {
      "hash_examples": "ea046ab2c6fc5928",
      "hash_full_prompts": "45f8422f6ad2da79",
      "hash_input_tokens": "211ca010114f2960",
      "hash_cont_tokens": "d350baad2daee8e7"
    },
    "truncated": 0,
    "non_truncated": 541,
    "padded": 0,
    "non_padded": 541,
    "num_truncated_few_shots": 0
  }
}